os-update-management
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions.
- Ingestion points: Package metadata and names are ingested via
homelab_aptUpgradable, and system logs are read viahomelab_aptHistory(SKILL.md). - Boundary markers: None identified. There are no explicit instructions for the agent to ignore natural language instructions that might be embedded in package descriptions or log entries.
- Capability inventory: The skill can perform system-level operations including package installation and upgrades (
homelab_aptUpdate), service management, and timer creation (homelab_systemdServices). - Sanitization: None identified. The skill does not describe mechanisms to sanitize or validate the content of the logs or package lists before processing them.
Audit Metadata